Application of neural network based on the genetic simulated annealing algorithm in failure diagnosis

被引：0

作者：

Hu Yu-lan ^{[1
]}

Fu Wen ^{[1
]}

Li Xue-mei ^{[1
]}

机构：

[1] Shenyang Ligong Univ, Fac Informat Sci & Engn, Shenyang 110168, Peoples R China

来源：

Proceedings of 2006 Chinese Control and Decision Conference | 2006年

关键词：

simulated annealing; genetic algorithm; BP algorithm; failure diagnosis;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The improved arithmetic de, signed is substituted for the backward propagation process of BP arithmetic. This optimized BP algorithm introduces simulated annealing algorithm to genetic algorithm and makes it be combined with multilayer perceptrons to form a compounding optimization perceptron. It is shown by simulated results that the improved arithmetic can greatly improve efficiency and accuracy of Internal Combustion Engine failure diagnosis system. The new perceptron has both the learning ability of the neural network and robustness, and strong random searching ability of genetic algorithm.

引用

页码：615 / 618

页数：4